Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Wang, Zhe"'
Publikováno v:
IEEE Access, Vol 9, Pp 60841-60852 (2021)
With the explosive increase of the types and quantity of devices in wireless networks, it is necessary to design a fast and energy-efficient decision-making strategy for the resource allocation to maintain the efficient operation of the wireless syst
Publikováno v:
2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID).
Anomaly detection is the primary method of detecting intrusion. Unsupervised models, such as auto-encoders network, auto-encoder, and GMM, are currently the most widely used anomaly detection techniques. In reality, the samples used to train the unsu
Publikováno v:
DCC
In this paper, we present a coding framework for deep convolutional neural network compression. Our approach utilizes the classical coding theories and formulates the compression of deep convolutional neural networks as a rate-distortion optimization
Publikováno v:
Applied Intelligence. 49:2659-2671
Marginal Fisher analysis (MFA) is an efficient method for dimension reduction, which can extract useful discriminant features for image recognition. Since sparse learning can achieve better generalization ability and lessen the amount of computations
Publikováno v:
2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS).
In recent years, smart grid has gradually become the common development trend of the world's power industry, and its security issues are increasingly valued by researchers. Smart grids have applied technologies such as physical control, data encrypti
Publikováno v:
2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP).
In recent years, some methods of learning Chinese word embedding based on the characters and sub-characters information have been proposed and achieve state-of-art results. Generally speaking, good embedding of characters and sub-characters can help
Publikováno v:
Journal of Visual Communication and Image Representation. 80:103312
Tracking-by-detection (TBD) is a significant framework for visual object tracking. However, current trackers are usually updated online based on random sampling with a probability distribution. The performance of the learning-based TBD trackers is li
Publikováno v:
Neural Networks. 81:59-71
This paper studies the learning and generalization performances of pseudo-inverse linear discriminant (PILDs) based on the processing minimum sum-of-squared error (MS 2 E) and the targeting overall classification accuracy (OCA) criterion functions. T
Publikováno v:
Laser & Optoelectronics Progress. 58:1615002
Publikováno v:
Laser & Optoelectronics Progress. 57:221003